Petabyte-Scale Row-Level Operations in Data Lakehouses

Summary: Adds petabyte-scale row-level updates/deletes to Iceberg+Spark via file-level materialization or lazy equality/position deletes. Avoids shuffles with storage-partitioned joins, cuts write amplification with runtime filters, and uses adaptive writes; shows use-case tradeoffs and ~10× gains. (summarized by gpt-5-mini on Feb 09 2026)

Paper ID: h3debeaa935333da5
Venue: VLDB
Year: 2024
Pagerank: 5.6441822e-05
Overall Rank: 6,920 | 53.48%
DOI: 10.14778/3685800.3685834

Incoming Non-self Citations Over Time

Authors

1. Anton Okolnychyi (Apple)
2. Chao Sun (Apple)
3. Kazuyuki Tanimura (Apple)
4. Russell Spitzer (Apple)
5. Ryan Blue (Tabular)
6. Szehon Ho (Apple)
7. Yufei Gu (Apple)
8. Vishwanath Lakkundi (Apple)
9. DB Tsai (Apple)

BibTeX Citation

@article{okolnychyi_vldb24,
        title = {{Petabyte-Scale Row-Level Operations in Data Lakehouses}},
        author = {Okolnychyi, Anton and Sun, Chao and Tanimura, Kazuyuki and Spitzer, Russell and Blue, Ryan and Ho, Szehon and Gu, Yufei and Lakkundi, Vishwanath and Tsai, DB},
        journal = {PVLDB},
        series = {{VLDB} '24},
        volume = {17},
        number = {12},
        pages = {4159--4172},
        doi = {10.14778/3685800.3685834},
        url = {https://doi.org/10.14778/3685800.3685834},
        year = {2024}
}

Incoming Citations (Sorted by Pagerank)

Showing 4 of 4 citing papers.

Rank	Citing Paper	Year	Venue	Pagerank
8,637	Magnus: A Holistic Approach to Data Management for Large-Scale Machine Learning Workloads	2025	VLDB	5.2978926e-05
9,021	AutoComp: Automated Data Compaction for Log-Structured Tables in Data Lakes	2025	SIGMOD	5.2349846e-05
10,227	TreeCat: Standalone Catalog Engine for Large Data Systems	2025	VLDB	5.0571508e-05
10,927	A Decade of Apache Spark Structured Streaming: How We Evolved The Architecture To Meet Real-World Needs	2026	VLDB	4.9793485e-05

Outgoing Citations (Sorted by Pagerank)

Showing 21 of 21 cited papers.

Citations counted here include only citations to other VLDB/SIGMOD/CIDR/PODS papers in this database.

Rank	Cited Paper	Year	Venue	Pagerank
12	C-Store: A Column-oriented DBMS	2005	VLDB	0.00068998927
14	MonetDB/X100: Hyper-Pipelining Query Execution	2005	CIDR	0.00064031282
19	A Critique of ANSI SQL Isolation Levels	1995	SIGMOD	0.00058781151
23	Spark SQL: Relational Data Processing in Spark	2015	SIGMOD	0.00055406774
52	The Snowflake Elastic Data Warehouse	2016	SIGMOD	0.00041219077
59	Differential Files: Their Application To The Maintenance Of Large Data Bases	1976	SIGMOD	0.00039605949
216	Small Materialized Aggregates: A Light Weight Index Structure for Data Warehousing	1998	VLDB	0.00024485024
233	Amazon Redshift and the Case for Simpler Data Warehouses	2015	SIGMOD	0.00023783585
237	Serializable Isolation for Snapshot Databases	2008	SIGMOD	0.00023660039
459	Delta Lake: High-Performance ACID Table Storage over Cloud Object Stores	2020	VLDB	0.00017856221
673	Hadoop++: Making a Yellow Elephant Run Like a Cheetah (Without It Even Noticing)	2010	VLDB	0.0001488755
950	Lakehouse: A New Generation of Open Platforms that Unify Data Warehousing and Advanced Analytics	2021	CIDR	0.00012895553
1,135	Dremel: A Decade of Interactive SQL Analysis at Web Scale	2020	VLDB	0.00011891907
1,632	Positional Update Handling in Column Stores	2010	SIGMOD	0.00010021251
2,687	CoHadoop: Flexible Data Placement and Its Exploitation in Hadoop	2011	VLDB	8.1301312e-05
3,446	Apache Hive: From MapReduce to Enterprise-grade Big Data Warehousing	2019	SIGMOD	7.2942885e-05
3,928	Big Metadata: When Metadata is Big Data	2021	VLDB	6.9192051e-05
4,332	Analyzing and Comparing Lakehouse Storage Systems	2023	CIDR	6.6587744e-05
5,504	Magnet: Push-based Shuffle Service for Large-scale Data Processing	2020	VLDB	6.1018427e-05
5,817	VectorH: Taking SQL-on-Hadoop to the Next Level	2016	SIGMOD	5.9840356e-05
8,208	LST-Bench: Benchmarking Log-Structured Tables in the Cloud	2024	SIGMOD	5.3775598e-05

Semantically Similar Papers

#	Overall Rank	Paper	Year	Venue
1	12,045	Pixels: Multiversion Wide Table Store for Data Lakes	2020	CIDR
2	4,530	BigLake: BigQuery’s Evolution toward a Multi-Cloud Lakehouse	2024	SIGMOD
3	9,021	AutoComp: Automated Data Compaction for Log-Structured Tables in Data Lakes	2025	SIGMOD
4	10,022	Towards Functional Decomposition of Storage Formats	2025	CIDR
5	459	Delta Lake: High-Performance ACID Table Storage over Cloud Object Stores	2020	VLDB
6	3,446	Apache Hive: From MapReduce to Enterprise-grade Big Data Warehousing	2019	SIGMOD
7	10,226	Active Data Lakes: Regaining Physical Data Independence Without Losing Interoperability	2026	VLDB
8	950	Lakehouse: A New Generation of Open Platforms that Unify Data Warehousing and Advanced Analytics	2021	CIDR
9	4,332	Analyzing and Comparing Lakehouse Storage Systems	2023	CIDR
10	5,348	Adaptive and Robust Query Execution for Lakehouses at Scale	2024	VLDB